© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 70959
    Prev
    Next
    INDEX
    Explanations

    job of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aleigh
    -0.08
    ppy
    -0.07
    柳
    -0.07
     сантим
    -0.07
     מדובר
    -0.07
    idered
    -0.07
    ноним
    -0.07
     kullanılan
    -0.07
    Slip
    -0.07
    typeparam
    -0.07
    POSITIVE LOGITS
    职责
    0.13
     duties
    0.13
     responsibility
    0.12
     পালন
    0.12
     Responsibilities
    0.12
    使命
    0.11
    Responsibilities
    0.11
     tarefa
    0.11
     Aufgabe
    0.11
     задача
    0.10
    Activations Density 0.064%

    No Known Activations